Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides an unmanned aerial vehicle inspection system based on a photovoltaic power station and an inspection method thereof, and the specific technical scheme is as follows:
on the one hand, provide an unmanned aerial vehicle system of patrolling and examining based on photovoltaic power plant, a serial communication port, include
The unmanned aerial vehicle is used for shooting images of the photovoltaic module and has a positioning function;
the server comprises a route planning module and a defect identification module, the route planning module can plan a routing inspection route for the unmanned aerial vehicle according to the position information of the photovoltaic module, and the defect identification module can screen out the defective photovoltaic module through an artificial intelligence image identification technology;
the flight task module is used for controlling the unmanned aerial vehicle, loading the inspection route from the server, and generating an independent inspection task according to the inspection route so as to control the unmanned aerial vehicle to execute a corresponding inspection task;
the defect addressing module is used for guiding operation and maintenance personnel to find the problem photovoltaic module by utilizing satellite positioning;
the unmanned aerial vehicle receives the task of patrolling and examining that the flight task module sent, it by flight task module control is followed the airline flight of patrolling and examining that corresponds to the image that will shoot passes through the flight task module uploads to the defect identification module, the defect identification module basis the problem photovoltaic module of image identification, the defect addressing module is followed the server downloads problem photovoltaic module's positional information to provide the navigation to the fortune dimension personnel.
Further, the unmanned aerial vehicle system further comprises an auxiliary maintenance robot, and if the auxiliary maintenance robot receives a warehouse-out instruction sent by the flight task module, the auxiliary maintenance robot carries the corresponding unmanned aerial vehicle out of the warehouse and moves the unmanned aerial vehicle to an air park;
and if the auxiliary maintenance robot receives the warehousing instruction sent by the flight task module, the auxiliary maintenance robot carries the corresponding unmanned aerial vehicle into the hangar from the parking apron.
Furthermore, the defect addressing module exists in the form of a handheld device, has a positioning function and is provided with a display screen, and the display screen is used for displaying the azimuth and distance relationship between the current position of the defect addressing module and the position of the problem photovoltaic module.
Further, the unmanned aerial vehicle can shoot two-dimensional or three-dimensional images, and position information corresponding to the unmanned aerial vehicle and the image information are transmitted back to the flight task module in real time when the images are shot.
On the other hand, the unmanned aerial vehicle inspection method based on the photovoltaic power station comprises the following steps:
s1, shooting a plurality of photovoltaic module images in the photovoltaic power station by using an unmanned aerial vehicle;
s2, calculating to obtain position information of each photovoltaic module according to the photovoltaic module image and parameter information corresponding to the unmanned aerial vehicle;
s3, planning an inspection route according to the position information of the photovoltaic module, and correspondingly generating an independent inspection task according to the inspection route;
s4, the unmanned aerial vehicle receives the inspection task, flies along the corresponding inspection route, shoots the photovoltaic module to be detected and transmits the shot image back to the server for processing;
and S5, screening out the problem photovoltaic modules by the server through an artificial intelligence image recognition technology, and informing corresponding operation and maintenance personnel.
Further, in step S3, the method for planning the patrol route includes:
according to the area and position information of the photovoltaic module to be detected and the shooting parameters of the unmanned aerial vehicle, correspondingly obtaining the optimal detection position of the photovoltaic module to be detected shot by the unmanned aerial vehicle before the unmanned aerial vehicle executes the inspection task;
and automatically generating a corresponding inspection route according to the plurality of optimal detection positions corresponding to the unmanned aerial vehicle.
Furthermore, before the unmanned aerial vehicle carries out the routing inspection task, the auxiliary maintenance robot receives a warehouse-out instruction, and carries the corresponding unmanned aerial vehicle out of the warehouse and starts the unmanned aerial vehicle so that the unmanned aerial vehicle receives the routing inspection task;
after the unmanned aerial vehicle finishes the routing inspection task, the unmanned aerial vehicle can automatically stop at an apron, the auxiliary maintenance robot receives the warehousing instruction, correspondingly carries the unmanned aerial vehicle into the hangar and shuts down the unmanned aerial vehicle, and then assists the unmanned aerial vehicle to charge or replace a battery.
Furthermore, the ex-warehouse instruction comprises the number information of the unmanned aerial vehicles about to execute the tasks, the unmanned aerial vehicles with different numbers are correspondingly placed at different positions of the hangar one by one, and the auxiliary maintenance robot finds the unmanned aerial vehicle at the corresponding position according to the number information of the unmanned aerial vehicle about to execute the tasks, moves the unmanned aerial vehicle out of the hangar and starts the unmanned aerial vehicle;
the warehousing instruction comprises the number information of the parked unmanned aerial vehicle, and the auxiliary maintenance robot carries the corresponding unmanned aerial vehicle into the corresponding position of the hangar according to the number information of the parked unmanned aerial vehicle.
Further, the unmanned aerial vehicle number in the inspection task can be checked by the unmanned aerial vehicle after the unmanned aerial vehicle is started, if the unmanned aerial vehicle number accords with the corresponding number and meets the flight electric quantity required by the inspection route, the unmanned aerial vehicle flies along the inspection route, and the photovoltaic modules to be detected on the inspection route are sequentially shot; if the unmanned aerial vehicle does not satisfy to accomplish and corresponds the required expected electric quantity of patrolling and examining the airline flight, then need to change the unmanned aerial vehicle of other numbers.
Further, the server compares the current image of the photovoltaic module with the corresponding historical image to screen out the problem photovoltaic module, the server classifies the defects of the screened problem photovoltaic module by means of artificial intelligence, packs the related information of the problem photovoltaic module with the same type of defects respectively, generates a corresponding inspection report, and informs corresponding operation and maintenance personnel.
Compared with the prior art, the invention has the following advantages:
a. the full-automatic inspection of the photovoltaic module in the photovoltaic power station is realized;
b. the efficiency of detecting the photovoltaic module is greatly improved;
c. the defects of the photovoltaic module can be automatically judged and automatically reported and repaired;
d. the photovoltaic module can assist operation and maintenance personnel to find corresponding problems.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions.
In an embodiment of the invention, an unmanned aerial vehicle inspection system based on a photovoltaic power station is provided, referring to fig. 1, the unmanned aerial vehicle inspection system comprises an unmanned aerial vehicle, a server, a flight task module and a defect addressing module, wherein the unmanned aerial vehicle has shooting and positioning functions and is used for shooting two-dimensional or three-dimensional images of a photovoltaic assembly and transmitting position information corresponding to the unmanned aerial vehicle and the image information back to the flight task module in real time when the images are shot; the server comprises a route planning module and a defect identification module, the route planning module can plan a routing inspection route for the unmanned aerial vehicle according to the position information of the photovoltaic module, and the defect identification module can screen out the photovoltaic module with problems through an artificial intelligence image identification technology; the flight task module loads the inspection route from the server and generates different inspection tasks according to the inspection route so as to control the unmanned aerial vehicle to execute corresponding inspection tasks; the defect addressing module guides operation and maintenance personnel to find the problem photovoltaic assembly by satellite positioning, the defect addressing module exists in the form of a handheld device, has a positioning function and is provided with a display screen, and the display screen is used for displaying the azimuth and distance relationship between the current position of the defect addressing module and the position of the problem photovoltaic assembly.
The unmanned aerial vehicle receives the inspection task sent by the flight task module, the inspection task module controls the inspection flight along the corresponding inspection air route, the shot image is uploaded to the defect identification module through the flight task module, the defect identification module identifies the problem photovoltaic module according to the image, and the defect addressing module downloads the position information of the problem photovoltaic module from the server so as to provide navigation for operation and maintenance personnel.
In order to assist the logistics work of the unmanned aerial vehicle, the unmanned aerial vehicle inspection system further comprises an auxiliary maintenance robot, if the auxiliary maintenance robot receives a warehouse-out instruction sent by the flight task module, and the warehouse-out instruction comprises the serial number of the unmanned aerial vehicle, the auxiliary maintenance robot carries the unmanned aerial vehicle with the corresponding serial number out of a warehouse, moves the unmanned aerial vehicle out of the warehouse, moves the unmanned aerial vehicle to an apron and starts the unmanned aerial vehicle; and if the auxiliary maintenance robot receives the warehousing instruction sent by the flight task module, wherein the warehousing instruction comprises the serial number of the unmanned aerial vehicle, the auxiliary maintenance robot carries the unmanned aerial vehicle with the corresponding serial number into an hangar from the parking apron, and shuts down the unmanned aerial vehicle to assist the unmanned aerial vehicle to replace a battery or charge the battery.
Aiming at photovoltaic power stations on plain or mountain lands, the unmanned aerial vehicle inspection system firstly obtains two-dimensional or three-dimensional image data by using an unmanned aerial vehicle, and identifies the position information of ground photovoltaic modules, such as GPS (global positioning system) position information, by using artificial intelligence so as to prefabricate the corresponding position information of all the photovoltaic modules; and calculating the GPS position where the unmanned aerial vehicle should be located when shooting according to the area and the position of the photovoltaic module to be detected and shooting parameters of the unmanned aerial vehicle, automatically processing the detection positions into the optimal routing inspection route, and recording the optimal routing inspection route into a database of the server.
According to the inspection route, an independent inspection task is generated, the unmanned aerial vehicle shoots photovoltaic modules to be detected according to the inspection task, the photovoltaic modules shot by the unmanned aerial vehicle are used as task results and uploaded to the server together with shot parameter information, then the problem photovoltaic modules are identified by artificial intelligence and then defect classification is carried out, a task conclusion is generated, GPS information of each problem photovoltaic module is recorded, and a task report is formed, wherein the types of the defects comprise the problems that the defects are blocked, the reflected light intensity is uneven, the diodes are damaged, and the like. After receiving a task report pushed by a server, operation and maintenance personnel of the photovoltaic power station download task data, select a problem photovoltaic module by using the handheld device, and know the direction and distance between the GPS coordinates of the handheld device and the position of the problem photovoltaic module so as to navigate to the problem photovoltaic module for maintenance.
Unmanned aerial vehicle system of patrolling and examining based on photovoltaic power plant that this embodiment provided can realize following function
(1) Artificial intelligent identification of photovoltaic modules on two-dimensional and three-dimensional maps
Sampling is carried out in a two-dimensional or three-dimensional mode, namely, two-dimensional or three-dimensional image shooting sampling is carried out in advance by using an unmanned aerial vehicle, the server identifies the photovoltaic module according to a sampling result, artificial intelligence is utilized, and according to image information, position information and shooting parameter information of the unmanned aerial vehicle during corresponding shooting, the GPS position information corresponding to the photovoltaic module is calculated, and a distribution coordinate graph of the photovoltaic module in the photovoltaic power station is prefabricated. Referring to fig. 2, the flight task module is used for controlling the unmanned aerial vehicle to shoot each photovoltaic module, namely photovoltaic power station image building and sampling operation is carried out, then image building operation data are uploaded to the server by the flight task module, the server processes and generates a two-dimensional or three-dimensional image of the photovoltaic power station, photovoltaic modules are identified in the image through artificial intelligence, and positions and various parameters are obtained by combining corresponding shooting of the unmanned aerial vehicle, so that position information of each photovoltaic module is obtained through calculation.
(2) Unmanned aerial vehicle inspection route planning
On the basis of artificial intelligence identification of the photovoltaic modules, the area and the position of the photovoltaic modules which need to be detected each time are determined by the route planning module, the shooting parameters of the unmanned aerial vehicle are combined, the GPS position where the unmanned aerial vehicle is supposed to be located when the unmanned aerial vehicle shoots is calculated, the detection positions are automatically processed to generate inspection routes, namely, waypoint flight routes or ground-imitating flight routes are recorded into the server database, a plurality of inspection routes can be generated in advance according to the positions of the photovoltaic modules, the photovoltaic modules in different areas can be detected among the inspection routes, the same cross photovoltaic modules of parts can be detected, a plurality of unmanned aerial vehicles can be dispatched to inspect along different inspection routes simultaneously, and the overall efficiency is improved.
It should be noted that the routing inspection routes can be pre-planned and can be temporarily planned, the pre-planning is that a plurality of routing inspection routes are preset in the system before the unmanned aerial vehicle is arranged to execute tasks, each routing inspection route can correspond to different routing inspection tasks because the photovoltaic modules to be detected on each routing inspection route are not identical, and the system can complete daily routine regular routing inspection through the pre-planned routing inspection routes and the preset task starting time without manual intervention;
the temporary planning is to wait to detect photovoltaic module and the route of patrolling and examining that temporarily generated according to one or several that power station personnel now selected to satisfy power station personnel and carry out the fixed point and detect, it is different from planning in advance, and temporary planning can make the direct quick photovoltaic module who waits to detect of flying to the target of unmanned aerial vehicle shoot, and need not detect other photovoltaic module by detour.
(3) Mountain region photovoltaic power plant unmanned aerial vehicle control and picture pass
Referring to fig. 3, the flight task module downloads the patrol route to the local through the internet, newly establishes a flight task, assigns a corresponding unmanned aerial vehicle to perform work shooting, transmits relevant detection information to the flight task module, and uploads detection data to the server through the internet after the flight task is finished. The flight mission module can be arranged on a remote controller or an operation computer.
(4) Artificial intelligence recognition of detection results
Referring to fig. 4, the defect identification module performs artificial intelligence identification on the detection data uploaded by the task to identify the defect and judge the type of the defect, records the GPS coordinate and the judgment conclusion of the problem photovoltaic module into the database of the task for identification, and generates a report and a coordinate record of the problem photovoltaic module.
(5) Automatic operation of unmanned aerial vehicle unmanned airport
Increase supplementary maintenance robot to unmanned on duty's photovoltaic power plant, refer to fig. 5, flight task module can give out the warehouse-out instruction to supplementary maintenance robot after sending the task of patrolling and examining, supplementary maintenance robot carries unmanned aerial vehicle to the parking apron and makes its start, refer to fig. 5, after confirming that unmanned aerial vehicle returns and descends to the specified area, the robot will automatic movement to the parking apron, discover and discern unmanned aerial vehicle, shift unmanned aerial vehicle to the hangar through specific fixing device, use the automatic device that trades of similar electric motor car in the hangar, carry out the battery to unmanned aerial vehicle and change, according to the task condition of accomplishing with unmanned aerial vehicle send back the parking apron and start or close the hangar.
(6) Report of handheld device and display of problem photovoltaic module coordinates
Referring to fig. 6, a defect addressing module downloads a detection report and detection result data of a specified task, the defect addressing module may be disposed on a mobile phone or other handheld devices with a GPS positioning function, an operation and maintenance worker views the report and can query GPS coordinates of a specified problem photovoltaic module, select a target problem photovoltaic module, then obtain a position of the operation and maintenance worker to navigate the target problem photovoltaic module, and then, after the operation and maintenance worker processes the target problem photovoltaic module, register a processing result on the device, and upload the processing result. It should be noted that the azimuth distance relationship between the problematic photovoltaic module GPS coordinates and the present device GPS coordinates can be compared on the handheld device screen to provide an image navigation display.
In one embodiment of the invention, an unmanned aerial vehicle inspection method based on a photovoltaic power station is provided, and is characterized by comprising the following steps:
s1, shooting a plurality of photovoltaic module images in the photovoltaic power station by using an unmanned aerial vehicle;
s2, calculating to obtain position information of each photovoltaic module according to the photovoltaic module image and parameter information corresponding to the unmanned aerial vehicle;
s3, planning an inspection route according to the position information of the photovoltaic module, and correspondingly generating an independent inspection task according to the inspection route;
s4, the unmanned aerial vehicle receives the inspection task, flies along the corresponding inspection route, shoots the photovoltaic module to be detected and transmits the shot image back to the server for processing;
and S5, screening out the problem photovoltaic modules by the server through an artificial intelligence image recognition technology, and informing corresponding operation and maintenance personnel.
The server compares the current image of the photovoltaic module with the corresponding historical image to screen out the problem photovoltaic module, the server classifies the defects of the screened problem photovoltaic module by means of artificial intelligence, packs the related information of the problem photovoltaic module with the same type of defects respectively, generates a corresponding inspection report, and informs corresponding operation and maintenance personnel, so that the operation and maintenance personnel can maintain the photovoltaic module with the same type of defects in a centralized manner, and can prepare materials required for maintenance in advance. Under different weather conditions, the server can call historical flight parameters and shooting parameters corresponding to a better task completion task of the unmanned aerial vehicle under the same or similar weather conditions before, and the control parameters are given to the flight task module so as to control the unmanned aerial vehicle to work quickly and stably.
The routing inspection route planning method comprises the following steps: according to the area and the position information of the photovoltaic module to be detected and in combination with shooting parameters of the unmanned aerial vehicle, the optimal detection position of the photovoltaic module to be detected is shot by the unmanned aerial vehicle before the unmanned aerial vehicle executes the inspection task, and according to the multiple optimal detection positions corresponding to the unmanned aerial vehicle, a corresponding inspection route is automatically generated.
In an embodiment of the invention, before the unmanned aerial vehicle performs the routing inspection task, the auxiliary maintenance robot receives an ex-warehouse instruction, and carries the corresponding unmanned aerial vehicle out of the hangar and starts up the corresponding unmanned aerial vehicle, so that the unmanned aerial vehicle receives the routing inspection task. The warehouse-out instruction comprises serial number information of unmanned aerial vehicles about to execute tasks, the unmanned aerial vehicles with different numbers are placed in different positions of the warehouse in a one-to-one correspondence mode, the auxiliary maintenance robot finds the unmanned aerial vehicles in corresponding positions according to the serial number information of the unmanned aerial vehicles about to execute the tasks, and moves out the unmanned aerial vehicles and enables the unmanned aerial vehicles to be started. The unmanned aerial vehicle number in the inspection task can be checked by the unmanned aerial vehicle after the unmanned aerial vehicle is started, if the unmanned aerial vehicle number accords with the corresponding number and meets the flight electric quantity required by the inspection route, the unmanned aerial vehicle flies along the inspection route, and the photovoltaic modules to be detected on the inspection route are shot in sequence; if the unmanned aerial vehicle does not satisfy to accomplish and corresponds the required expected electric quantity of patrolling and examining the airline flight, then need to change the unmanned aerial vehicle of other numbers.
After the unmanned aerial vehicle finishes the routing inspection task, the unmanned aerial vehicle can automatically stop at an apron, the auxiliary maintenance robot receives the warehousing instruction, correspondingly carries the unmanned aerial vehicle into the hangar and shuts down the unmanned aerial vehicle, and then assists the unmanned aerial vehicle to charge or replace a battery. The storage command comprises the number information of the stopped unmanned aerial vehicle, and the auxiliary maintenance robot carries the corresponding unmanned aerial vehicle into the corresponding position of the hangar according to the number information of the stopped unmanned aerial vehicle.
This implementation will not carry out the unmanned aerial vehicle of task and put at the hangar, need the during operation shift out the hangar again, has realized unmanned on duty, has prolonged unmanned aerial vehicle's life when using effectively, and has guaranteed unmanned aerial vehicle possesses sufficient electric quantity when carrying out the task.
The unmanned aerial vehicle inspection system and the inspection method thereof based on the photovoltaic power station provided by the invention provide a simple and rapid unmanned aerial vehicle inspection scheme aiming at the requirements of different users and different roles, and the detection result is directly applied to production, so that the time consumption is short, the efficiency is high, and the requirement on the professional performance of personnel is low.
The above description is only for the preferred embodiment of the present invention and is not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes that can be directly or indirectly applied to other related technical fields using the contents of the present specification and the accompanying drawings are included in the scope of the present invention.